Financial named entity recognition based on conditional random fields and information entropy

Shuwei Wang; Ruifeng Xu; Bin Liu; Lin Gui; Yu Zhou

doi:10.1109/ICMLC.2014.7009718

Financial named entity recognition based on conditional random fields and information entropy

Shuwei Wang, Ruifeng Xu^*, Bin Liu, Lin Gui, Yu Zhou

^*Corresponding author for this work

Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

15 Citations (Scopus)

Abstract

Named entity recognition plays an important role in many natural language processing tasks, such as relation detection and information extraction. This paper presents a novel method to recognize named entities infinancial news texts in three steps. First, the domain dictionary is applied to recognize stock names. Second, the full form FNEs are identified by incorporating internal features in a classifier based on Conditional Random Fields. Third, the mutual information, boundary entropy and context features are employed to recognize the abbreviation FNE candidates. The experiments completed on a Chinese financial dataset show that the proposed approach achieves 91.02% precision and 92.77% recall.

Original language	English
Title of host publication	Proceedings of 2014 International Conference on Machine Learning and Cybernetics, ICMLC 2014
Publisher	IEEE Computer Society
Pages	838-843
Number of pages	6
ISBN (Electronic)	9781479942169
DOIs	https://doi.org/10.1109/ICMLC.2014.7009718
Publication status	Published - 13 Jan 2014
Externally published	Yes
Event	13th International Conference on Machine Learning and Cybernetics, ICMLC 2014 - Lanzhou, China Duration: 13 Jul 2014 → 16 Jul 2014

Publication series

Name	Proceedings - International Conference on Machine Learning and Cybernetics
Volume	2
ISSN (Print)	2160-133X
ISSN (Electronic)	2160-1348

Conference

Conference	13th International Conference on Machine Learning and Cybernetics, ICMLC 2014
Country/Territory	China
City	Lanzhou
Period	13/07/14 → 16/07/14

Keywords

Conditional Random Fields
Financial named entity
Information Entropy
Named entities recognition

Access to Document

10.1109/ICMLC.2014.7009718

Cite this

Wang, S., Xu, R., Liu, B., Gui, L., & Zhou, Y. (2014). Financial named entity recognition based on conditional random fields and information entropy. In Proceedings of 2014 International Conference on Machine Learning and Cybernetics, ICMLC 2014 (pp. 838-843). Article 7009718 (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 2). IEEE Computer Society. https://doi.org/10.1109/ICMLC.2014.7009718

@inproceedings{f6c96aabfb674f628f6661fb924d2f57,

title = "Financial named entity recognition based on conditional random fields and information entropy",

abstract = "Named entity recognition plays an important role in many natural language processing tasks, such as relation detection and information extraction. This paper presents a novel method to recognize named entities infinancial news texts in three steps. First, the domain dictionary is applied to recognize stock names. Second, the full form FNEs are identified by incorporating internal features in a classifier based on Conditional Random Fields. Third, the mutual information, boundary entropy and context features are employed to recognize the abbreviation FNE candidates. The experiments completed on a Chinese financial dataset show that the proposed approach achieves 91.02% precision and 92.77% recall.",

keywords = "Conditional Random Fields, Financial named entity, Information Entropy, Named entities recognition",

author = "Shuwei Wang and Ruifeng Xu and Bin Liu and Lin Gui and Yu Zhou",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 13th International Conference on Machine Learning and Cybernetics, ICMLC 2014 ; Conference date: 13-07-2014 Through 16-07-2014",

year = "2014",

month = jan,

day = "13",

doi = "10.1109/ICMLC.2014.7009718",

language = "English",

series = "Proceedings - International Conference on Machine Learning and Cybernetics",

publisher = "IEEE Computer Society",

pages = "838--843",

booktitle = "Proceedings of 2014 International Conference on Machine Learning and Cybernetics, ICMLC 2014",

address = "United States",

}

Wang, S, Xu, R, Liu, B, Gui, L & Zhou, Y 2014, Financial named entity recognition based on conditional random fields and information entropy. in Proceedings of 2014 International Conference on Machine Learning and Cybernetics, ICMLC 2014., 7009718, Proceedings - International Conference on Machine Learning and Cybernetics, vol. 2, IEEE Computer Society, pp. 838-843, 13th International Conference on Machine Learning and Cybernetics, ICMLC 2014, Lanzhou, China, 13/07/14. https://doi.org/10.1109/ICMLC.2014.7009718

Financial named entity recognition based on conditional random fields and information entropy. / Wang, Shuwei; Xu, Ruifeng; Liu, Bin et al.
Proceedings of 2014 International Conference on Machine Learning and Cybernetics, ICMLC 2014. IEEE Computer Society, 2014. p. 838-843 7009718 (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Financial named entity recognition based on conditional random fields and information entropy

AU - Wang, Shuwei

AU - Xu, Ruifeng

AU - Liu, Bin

AU - Gui, Lin

AU - Zhou, Yu

PY - 2014/1/13

Y1 - 2014/1/13

N2 - Named entity recognition plays an important role in many natural language processing tasks, such as relation detection and information extraction. This paper presents a novel method to recognize named entities infinancial news texts in three steps. First, the domain dictionary is applied to recognize stock names. Second, the full form FNEs are identified by incorporating internal features in a classifier based on Conditional Random Fields. Third, the mutual information, boundary entropy and context features are employed to recognize the abbreviation FNE candidates. The experiments completed on a Chinese financial dataset show that the proposed approach achieves 91.02% precision and 92.77% recall.

AB - Named entity recognition plays an important role in many natural language processing tasks, such as relation detection and information extraction. This paper presents a novel method to recognize named entities infinancial news texts in three steps. First, the domain dictionary is applied to recognize stock names. Second, the full form FNEs are identified by incorporating internal features in a classifier based on Conditional Random Fields. Third, the mutual information, boundary entropy and context features are employed to recognize the abbreviation FNE candidates. The experiments completed on a Chinese financial dataset show that the proposed approach achieves 91.02% precision and 92.77% recall.

KW - Conditional Random Fields

KW - Financial named entity

KW - Information Entropy

KW - Named entities recognition

UR - http://www.scopus.com/inward/record.url?scp=84921502704&partnerID=8YFLogxK

U2 - 10.1109/ICMLC.2014.7009718

DO - 10.1109/ICMLC.2014.7009718

M3 - Conference contribution

AN - SCOPUS:84921502704

T3 - Proceedings - International Conference on Machine Learning and Cybernetics

SP - 838

EP - 843

BT - Proceedings of 2014 International Conference on Machine Learning and Cybernetics, ICMLC 2014

PB - IEEE Computer Society

T2 - 13th International Conference on Machine Learning and Cybernetics, ICMLC 2014

Y2 - 13 July 2014 through 16 July 2014

ER -

Wang S, Xu R, Liu B, Gui L, Zhou Y. Financial named entity recognition based on conditional random fields and information entropy. In Proceedings of 2014 International Conference on Machine Learning and Cybernetics, ICMLC 2014. IEEE Computer Society. 2014. p. 838-843. 7009718. (Proceedings - International Conference on Machine Learning and Cybernetics). doi: 10.1109/ICMLC.2014.7009718

Financial named entity recognition based on conditional random fields and information entropy

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this